Human Face Recognition Using Different Moment Invariants: A Comparative Study

Human face recognition has recently become one of the hottest topics in the area of pattern recognition due to its applications in identity validation and recognition. Moment Invariants are pattern sensitive features and are used in pattern recognition applications. In this paper different moment invariants have been used to extract features from human face images for recognition application.  Moment invariants of Hu (HMI), Bamieh (BMI), Zernike (ZMI), Pseudo Zernike (PZMI), Teague-Zernike (TZMI), Normalized Zernike (NZMI) ,Normalized Pseudo Zernike (NPZMI) and also regular Moment Invariant (RMI) have been applied to the AT&T face database and the results have been compared. Our results show that pseudo Zernike moments yields the best recognition accuracy of 95%.